Sighted by Default: Addressing Implicit Vision Assumptions in Real-Time VLM Assistance for BLV Users
On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Abstract (arXiv)
Vision-Language Model (VLM)-based assistance is reshaping independence for blind and low-vision (BLV) users, yet current tools fail in dynamic settings. While request-response architectures like BeMyAI impose prohibitive latencies, our formative study (N = 15) reveals that even real-time alternatives like Doubao fail due to a deeper structural problem: sighted-default bias -- the implicit assumption that users possess parallel visual access to their surroundings. This bias manifests as verbose, vision-centric narratives that overlook the serial nature of auditory perception, flooding the user's limited cognitive bandwidth with information that is neither timely nor actionable. To address this, we derive three design principles: Continuity, Conciseness, and Calibrated Honesty. We present VIA-Agent, which co-optimizes a specialized cognitive core with a low-latency Real-Time Communication (RTC) architecture for continuous bidirectional streaming. In a within-subjects evaluation (N = 9), VIA-Agent matched Doubao's success rate, significantly reducing mean task time by 21.4% (91.7s vs. 116.7s) and conversational turns from 5.9 to 4.3 while achieving higher trust.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. First posted on arXiv 2 Nov 2025.
Builds on
No reference list yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Small yet Assistive: Spatially-Aware Post-Training for Low Vision
- 2025Are Large Vision-Language Models Ready to Guide Blind and Low-Vision Individuals?
- 2026Exploring the Use of VLMs for Navigation Assistance for People with Blindness and Low Vision
- 2026VIABench: A Comprehensive Video Benchmark Collected from Blind Individuals for Visual Impairment Assistance
- 2026How Multimodal Large Language Models Support Access to Visual Information: A Diary Study With Blind and Low Vision People
- 2025Not There Yet: Evaluating Vision Language Models in Simulating the Visual Perception of People with Low Vision
- 2026Explainable AI for Blind and Low-Vision Users: Navigating Trust, Modality, and Interpretability in the Agentic Era
- 2026Time-Aware Assistive Navigation